{"id":"W2907786475","doi":"10.1109/icosc.2019.8665673","title":"Improving Tree-LSTM with Tree Attention","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Tree (set theory); Computer science; Tree structure; Artificial intelligence; Dependency (UML); Encoding (memory); Task (project management); Sentence; Decision tree model; Natural language processing; Machine learning; Theoretical computer science; Decision tree; Algorithm; Mathematics; Binary tree","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002209838,0.0002360461,0.000253318,0.00009071457,0.00004474562,0.0003226236,0.001273675,0.0001803965,0.00001883227],"category_scores_gemma":[0.000009411779,0.0001834066,0.0001005391,0.00009134779,0.00001466714,0.0002698892,0.001649673,0.0004050168,0.0001048312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008420132,"about_ca_system_score_gemma":0.0001849883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004540696,"about_ca_topic_score_gemma":0.0002353617,"domain_scores_codex":[0.9981849,0.00003719141,0.0002530954,0.0008853866,0.0003608113,0.0002786244],"domain_scores_gemma":[0.9980528,0.00002814319,0.0001842888,0.001582661,0.00008558356,0.0000665585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001231109,0.00008401426,0.00583586,0.000403852,0.0000952421,0.00003059546,0.0004832116,0.01389815,0.001630758,0.04778386,0.0005821799,0.92916],"study_design_scores_gemma":[0.0002847805,0.00004898147,0.003293746,0.0001078413,0.00001524006,0.000009862261,0.0000174391,0.9934765,0.0002427589,0.001947403,0.0002010729,0.0003544436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02311333,0.00004728944,0.9478826,0.0006705598,0.0008843713,0.0003184807,7.60198e-7,0.0003561118,0.0267265],"genre_scores_gemma":[0.6780964,0.000004296126,0.3128995,0.0001658858,0.0001599483,0.00002395152,0.000006670849,0.00001769743,0.008625655],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9795783,"threshold_uncertainty_score":0.7479104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02104007912626795,"score_gpt":0.2296056283248885,"score_spread":0.2085655491986205,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}